Verdict
Claude Opus 4.7 leads 16–4 across 20 shared benchmarks.
Claude Opus 4.6 4 · Claude Opus 4.7 16 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: Claude Opus 4.6 leads 3–2 across 5 shared reasoning benchmarks (largest gap: SimpleBench, 61.12 vs 55.48 — single evaluator).
Unknown: Claude Opus 4.7 leads 3–0 across 3 shared unknown benchmarks (largest gap: EBR-bench, 19.05 vs 12.7 — single evaluator).
Coding: Claude Opus 4.7 leads 2–0 across 2 shared coding benchmarks (largest gap: FrontierCode, 38.5 vs 26.64 — single evaluator).
Math: Claude Opus 4.7 leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 31.71 vs 26.83 — single evaluator).
Vendor claims — compare against the measured scores above. A claim is what a developer says about its own model, not an independent measurement.
Coding
“The new Claude Opus 4.6 improves on its predecessor's coding skills”
Agentic / Tool Use
“Users report being able to hand off their hardest coding work-the kind that previously needed close supervision-to Opus 4.7 with confidence”
Coding
“Opus 4.7 is a notable improvement on Opus 4.6 in advanced software engineering, with particular gains on the most difficult tasks”
Reasoning
“Second, Opus 4.7 thinks more at higher effort levels, particularly on later turns in agentic settings”
Claude Opus 4.7 leads 16–4 across 20 shared benchmarks. Claude Opus 4.6 leads 4 benchmarks and Claude Opus 4.7 leads 16. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 4.6 and Claude Opus 4.7 have 20 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Claude Opus 4.7 leads unknown 3–0. Claude Opus 4.7 leads coding 2–0.